Deep Learning for Liver Anatomy Segmentation

2023-05824 - Deep Learning for Liver Anatomy Segmentation

Level of qualifications required : Master's or equivalent

Other valued qualifications : Master of Science

Fonction : Internship Research

Context

The project is an ongoing collaboration between Guerbet Group, Inria, Paul Brousse Hospital, and Université Paris-Saclay. The internship will be academically co-supervised by: Irene Vignon-Clementel (DR), and Omar Ali (PhD Candidate).

Assignment

Liver cancer is the second most common cause of cancer-related deaths worldwide. The French-based company Guerbet is a leader in medical imaging with an AI team expert in image analysis. The basis of the model is the segmentation of the liver anatomy (parenchyma, tumors, vessels) from CT scans. However, even with the highest CT scan resolution, in a clinical context, tumors can be difficult to spot, and only a few vessel branches are detectable, making the segmentation of these regions challenging. Therefore, further improvements are required to generate better liver anatomy segmentations which are useful for liver surgery risk prediction, planning and diagnosis.

The main scientific objectives of this internship are to develop an AI model(s) with new architectures/loss functions to ensure accurate liver tumor segmentations and continuous liver vessel tree connections. These segmentations will be helpful to liver surgeons in their preoperative assessment of the situation of the patient.

Bibliography

European Association for the Study of the Liver. Electronic address: [email protected]; European Association for the Study of the Liver. EASL Clinical Practice Guidelines: Management of hepatocellular carcinoma. J Hepatol. 2018 Jul;69(1):182-236.

Ali, A. Bone, M. -M. Rohe, E. Vibert and I. Vignon-Clementel, "Learning to Jointly Segment the Liver, Lesions and Vessels from Partially Annotated Datasets," 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France, 2022, pp. 3626-3630

Ali, O. et al. (2022). CoRe: An Automated Pipeline for the Prediction of Liver Resection Complexity from Preoperative CT Scans. In: , et al. Artificial Intelligence over Infrared Images for Medical Applications and Medical Image Assisted Biomarker Discovery. MIABID AIIIMA 2022 2022. Lecture Notes in Computer Science, vol 13602. Springer, Cham.

Main activities

The expected task requirements include:

Implement and test a topologically preserving loss function for vessel segmentations in nnUNet

Investigate weakly supervised approaches for liver vessel segmentation

Use Vision Transformers (i.e., UnetR, SwinUNetR) coded in MONAI for liver lesion segmentation

Implement trained vessel/tumor models for liver surgery risk prediction

Skills

Technical skills and level required : Python, PyTorch, TensorFlow, and Github are a plus.

Languages : English (Fluent)

Benefits package

Subsidized meals

Partial reimbursement of public transport costs

Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)

Possibility of teleworking (after 6 months of employment) and flexible organization of working hours

Professional equipment available (videoconferencing, loan of computer equipment, etc.)

Social, cultural and sports events and activities

Access to vocational training

Social security coverage

General Information

Theme/Domain : Optimization, machine learning and statistical methods Scientific computing (BAP E)

Town/city : Palaiseau

Inria Center : Centre Inria de Saclay

Starting date : 2023-04-24

Duration of contract : 6 months

Deadline to apply : 2023-03-31

Contacts

Inria Team : SIMBIOTX

Recruiter : Vignon Clementel Irene / [email protected]

The keys to success

We are looking for motivated candidates with a background in deep/machine learning, strong analytical and problem-solving skills, and experience in developing Python scripts. Experience in medical imaging and big data is encouraged. Knowledge about modeling is a plus. Fluency in English is preferred.

About Inria

Inria is the French national research institute dedicated to digital science and technology. It employs 2,600 people. Its 200 agile project teams, generally run jointly with academic partners, include more than 3,500 scientists and engineers working to meet the challenges of digital technology, often at the interface with other disciplines. The Institute also employs numerous talents in over forty different professions. 900 research support staff contribute to the preparation and development of scientific and entrepreneurial projects that have a worldwide impact.

Instruction to apply

Defence Security : This position is likely to be situated in a restricted area (ZRR), as defined in Decree No. 2011-1425 relating to the protection of national scientific and technical potential (PPST).Authorisation to enter an area is granted by the director of the unit, following a favourable Ministerial decision, as defined in the decree of 3 July 2012 relating to the PPST. An unfavourable Ministerial decision in respect of a position situated in a ZRR would result in the cancellation of the appointment.

Recruitment Policy : As part of its diversity policy, all Inria positions are accessible to people with disabilities.

Warning : you must enter your e-mail address in order to save your application to Inria. Applications must be submitted online on the Inria website. Processing of applications sent from other channels is not guaranteed.